execute

A command for the third phase of a development workflow: building an approved plan. It checks a project gate, reads the written decisions, and tells the agent how strictly to follow or extend them.

In plain words
What is it for?
Use it to implement a feature after planning and research are complete. It helps an agent check project status, read decisions, and apply, infer from, improve, or defer proposed choices.
Why use it?
It prevents coding from starting when research has not been approved and limits decisions that were already settled. It also sets a quality standard for the files being written.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/rchase999/aidd/execute
Clone the repo
git clone --depth 1 https://github.com/rchase999/aidd
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,491 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.01491
Opus 5 $0.00010 $0.00745
Sonnet 5 $0.00004 $0.00298
Haiku 4.5 $0.00002 $0.00149

Measured yesterday against content hash e0bb5d9e1ed1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

aidd/commands/execute.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 3 — Execute

Load the execution-charter skill, and the craft-bar skill — the craft bar is not optional, and it applies from the first file you write.

Focus for this run: $ARGUMENTS

Gate check — do this first

!node "${CLAUDE_PLUGIN_ROOT}/scripts/aidd.mjs" status 2>&1

If gate is not passed, stop and run /aidd:gate. Building against research the user never signed off on is the exact failure this framework exists to prevent.

Read the contract

Read .aidd/02-research/decisions.md completely — including the machine-readable block at the bottom — before touching a file. Then obey it:

Stance Your latitude
APPLY None on the choice itself. Build exactly this. If it turns out to be unworkable, stop and tell the user — do not silently substitute.
INFER Read it, take what's useful, then decide for yourself. Do not reproduce it wholesale; if your answer looks identical to the referenced option, you inferred nothing.
INNOVATE The named option is the ground already covered. Go somewhere else and make it better. Say plainly what you did instead and why it beats the option shown.
DEFERRED Your call. Pick what the research supports, record the pick and the reason, tag it [claude-call].
LOCKED Not a choice — a fact about the codebase. Build with it. Replacing it is a separate project and needs the user's say-so.

If the contract has a What the existing codebase already fixes section, read it as binding too. The must not break list is the highest-priority constraint in the whole document: breaking the revenue path is worse than shipping nothing.

In brownfield mode, add these rules:

  • Match the surrounding code. Its naming, layering, error handling, and test style — even where you would have done it differently. Consistency is worth more than your preference, and mismatched style is how generated code announces itself.
  • No opportunistic refactors. If you spot something worth fixing outside this change's scope, note it for the user instead of doing it. A diff that touches twice what it needed to is a diff nobody can review.
  • Extend the existing seams rather than adding parallel ones. A second job runner, a second config system, or a second HTTP client beside the one already there is a defect, not an improvement.
  • Migrations and public contracts are one-way doors. Additive first; anything destructive gets raised before it is written.

Read the full file on GitHub · 80 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 80 lines · 19 tokens per session scan A e0bb5d9e1ed1

Subscribe to this mod's changes

execute is a command published in the GitHub repository rchase999/aidd (2 stars, last pushed 23d ago), licensed MIT. It adds 19 tokens to every session and 1,491 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.